English
Related papers

Related papers: Model Merging and Safety Alignment: One Bad Model …

200 papers

Large language models (LLMs) have rapidly become familiar tools to researchers and practitioners. Concepts such as prompting, temperature, or few-shot examples are now widely recognized, and LLMs are increasingly used in Modeling &…

Artificial Intelligence · Computer Science 2026-02-06 Philippe J. Giabbanelli

Fine-tuning pre-trained models with custom data leads to numerous expert models on specific tasks. Merging models into one universal model to empower multi-task ability refraining from data leakage has gained popularity. With the expansion…

Computer Vision and Pattern Recognition · Computer Science 2025-12-16 Fanhu Zeng , Haiyang Guo , Fei Zhu , Li Shen , Hao Tang

Recent research has increasingly focused on reconciling the reasoning capabilities of System 2 with the efficiency of System 1. While existing training-based and prompt-based approaches face significant challenges in terms of efficiency and…

Computation and Language · Computer Science 2025-11-17 Yuxuan Yao , Shuqi Liu , Zehua Liu , Qintong Li , Mingyang Liu , Xiongwei Han , Zhijiang Guo , Han Wu , Linqi Song

The safety alignment of current Large Language Models (LLMs) is vulnerable. Relatively simple attacks, or even benign fine-tuning, can jailbreak aligned models. We argue that many of these vulnerabilities are related to a shared underlying…

Cryptography and Security · Computer Science 2024-06-11 Xiangyu Qi , Ashwinee Panda , Kaifeng Lyu , Xiao Ma , Subhrajit Roy , Ahmad Beirami , Prateek Mittal , Peter Henderson

Instruction tuning is crucial for optimizing Large Language Models (LLMs), yet mainstream data selection methods heavily rely on LLMs as instruction quality scorers, leading to high computational costs and reduced data diversity. To address…

Machine Learning · Computer Science 2025-03-04 Hongyi Cai , Yuqian Fu , Hongming Fu , Bo Zhao

While Large Language Models (LLMs) have seen widespread applications across numerous fields, their limited interpretability poses concerns regarding their safe operations from multiple aspects, e.g., truthfulness, robustness, and fairness.…

Software Engineering · Computer Science 2024-04-15 Xuan Xie , Jiayang Song , Zhehua Zhou , Yuheng Huang , Da Song , Lei Ma

As large language models continue to scale up, knowledge editing techniques that modify models' internal knowledge without full retraining have gained significant attention. MEMIT, a prominent batch editing algorithm, stands out for its…

Computation and Language · Computer Science 2025-09-10 Zilu Dong , Xiangqing Shen , Rui Xia

Ensuring the safe alignment of large language models (LLMs) with human values is critical as they become integral to applications like translation and question answering. Current alignment methods struggle with dynamic user intentions and…

Computation and Language · Computer Science 2024-10-29 Rima Hazra , Sayan Layek , Somnath Banerjee , Soujanya Poria

Continual learning (CL) is essential for deploying large language models (LLMs) in dynamic real-world environments without the need for costly retraining. Recent model merging-based methods have attracted significant attention, but they…

Computation and Language · Computer Science 2025-09-23 Yujie Feng , Jian Li , Xiaoyu Dong , Pengfei Xu , Xiaohui Zhou , Yujia Zhang , Zexin LU , Yasha Wang , Alan Zhao , Xu Chu , Xiao-Ming Wu

Large Language Models (LLMs) have exploded a new heatwave of AI for their ability to engage end-users in human-level conversations with detailed and articulate answers across many knowledge domains. In response to their fast adoption in…

Optimization algorithms and large language models (LLMs) enhance decision-making in dynamic environments by integrating artificial intelligence with traditional techniques. LLMs, with extensive domain knowledge, facilitate intelligent…

Neural and Evolutionary Computing · Computer Science 2024-05-17 Sen Huang , Kaixiang Yang , Sheng Qi , Rui Wang

Recent developments in Large Language Models (LLMs) have manifested significant advancements. To facilitate safeguards against malicious exploitation, a body of research has concentrated on aligning LLMs with human preferences and…

Cryptography and Security · Computer Science 2024-06-11 Yuanpu Cao , Bochuan Cao , Jinghui Chen

Fine-tuning pre-trained models for downstream tasks has led to a proliferation of open-sourced task-specific models. Recently, Model Merging (MM) has emerged as an effective approach to facilitate knowledge transfer among these…

Cryptography and Security · Computer Science 2024-09-04 Jinghuai Zhang , Jianfeng Chi , Zheng Li , Kunlin Cai , Yang Zhang , Yuan Tian

Large language models (LLMs) hold promise for transforming healthcare, from streamlining administrative and clinical workflows to enriching patient engagement and advancing clinical decision-making. However, their successful integration…

Computers and Society · Computer Science 2025-04-04 Mohammed Al-Garadi , Tushar Mungle , Abdulaziz Ahmed , Abeed Sarker , Zhuqi Miao , Michael E. Matheny

Aligning large language models (LLMs) through supervised fine-tuning is essential for tailoring them to specific applications. Recent studies suggest that alignment primarily adjusts a model's presentation style rather than its foundational…

Computation and Language · Computer Science 2025-04-09 Guangyuan Shi , Zexin Lu , Xiaoyu Dong , Wenlong Zhang , Xuanyu Zhang , Yujie Feng , Xiao-Ming Wu

Large language models (LLMs) undergo safety alignment to ensure safe conversations with humans. However, this paper introduces a training-free attack method capable of reversing safety alignment, converting the outcomes of stronger…

Computation and Language · Computer Science 2024-06-07 Zhanhui Zhou , Jie Liu , Zhichen Dong , Jiaheng Liu , Chao Yang , Wanli Ouyang , Yu Qiao

Model merging provides a compelling paradigm for integrating specialized expertise into a unified multi-task model, a goal that aligns naturally with the sequential knowledge acquisition in continual learning (CL). However, the requirement…

Machine Learning · Computer Science 2026-05-12 Xi Wang , Cheng Deng

The planning ability of Large Language Models (LLMs) has garnered increasing attention in recent years due to their remarkable capacity for multi-step reasoning and their ability to generalize across a wide range of domains. While some…

Artificial Intelligence · Computer Science 2025-02-19 Mohamed Aghzal , Erion Plaku , Gregory J. Stein , Ziyu Yao

Multimodal Large Language Models (MLLMs) rely on multimodal pre-training over diverse data sources, where different datasets often induce complementary cross-modal alignment capabilities. Model merging provides a cost-effective mechanism…

Computer Vision and Pattern Recognition · Computer Science 2026-04-28 Zibo Shao , Baochen Xiong , Xiaoshan Yang , Yaguang Song , Qimeng Zhang , Haifeng Chen , Changsheng Xu

We present a surprising result regarding LLMs and alignment. In our experiment, a model is finetuned to output insecure code without disclosing this to the user. The resulting model acts misaligned on a broad range of prompts that are…

Computation and Language · Computer Science 2026-01-27 Jan Betley , Daniel Tan , Niels Warncke , Anna Sztyber-Betley , Xuchan Bao , Martín Soto , Nathan Labenz , Owain Evans
‹ Prev 1 8 9 10 Next ›